Author name: Meilun Zhou, Alina Zare

arXiv:2604.03837v1 Announce Type: new
Abstract: Prior multi-task triplet loss methods relied on static weights to balance supervision between various types of annotation. However, static weighting requires tuning and does not account for how tasks int…

arXiv:2604.03839v1 Announce Type: new
Abstract: Task-driven features learned by modern object detectors optimize end task loss yet often capture shortcut correlations that fail to reflect underlying annotation structure. Such representations limit tra…